A Digital Twin Approach for Fault Diagnosis in Unmanned Ships Integrated Power System

Abstract

The Integrated Power System (IPS) of unmanned ship has integrated various equipment and thus has a complex structure. Current fault diagnosis approaches rely heavily on fault history data and case-by-case models, making it difficult for unattended operation. This paper proposes a model-free fault diagnosis method based on Digital Twin (DT) system. The rule-based discriminative approach is adopted to efficiently identify system faults and their type without the need for historical data or specific physical models. The unmanned ship IPS is modeled on the RTLAB hardware-in-the-loop simulation platform, and the DT system is established on Simulink. Case study about diagnosing the propulsion branch faults on unmanned ships is performed. The results show that the proposed method can quickly detect system faults accurately identify the specific damaged equipment.